SASV 2022: The First Spoofing-Aware Speaker Verification Challenge

View on arXiv ← Back to list

Authors: Jee-weon Jung, Hemlata Tak, Hye-jin Shim, Hee-Soo Heo, Bong-Jin Lee, Soo-Whan Chung, Ha-Jin Yu, Nicholas Evans, Tomi Kinnunen

Published: 2022-03-28 13:19:14+00:00

AI Summary

The paper presents the first Spoofing-Aware Speaker Verification (SASV) challenge, aiming to integrate speaker verification and anti-spoofing research. The challenge focuses on jointly optimized solutions, contrasting with previous challenges that treated these as separate tasks. Results show that the top-performing system significantly reduces the equal error rate compared to a conventional system.

Abstract

The first spoofing-aware speaker verification (SASV) challenge aims to integrate research efforts in speaker verification and anti-spoofing. We extend the speaker verification scenario by introducing spoofed trials to the usual set of target and impostor trials. In contrast to the established ASVspoof challenge where the focus is upon separate, independently optimised spoofing detection and speaker verification sub-systems, SASV targets the development of integrated and jointly optimised solutions. Pre-trained spoofing detection and speaker verification models are provided as open source and are used in two baseline SASV solutions. Both models and baselines are freely available to participants and can be used to develop back-end fusion approaches or end-to-end solutions. Using the provided common evaluation protocol, 23 teams submitted SASV solutions. When assessed with target, bona fide non-target and spoofed non-target trials, the top-performing system reduces the equal error rate of a conventional speaker verification system from 23.83% to 0.13%. SASV challenge results are a testament to the reliability of today's state-of-the-art approaches to spoofing detection and speaker verification.

Key findings

The top-performing system achieved an equal error rate (EER) of 0.13%, a substantial reduction from the 23.83% EER of a conventional speaker verification system. Many participating systems outperformed the challenge baselines, demonstrating the benefit of integrating speaker verification and anti-spoofing techniques.

Approach

The SASV challenge encourages two approaches: back-end fusion of independently trained speaker verification and anti-spoofing models, and end-to-end integrated solutions. Participants submitted systems using provided baseline models and a common evaluation protocol.

Datasets

VoxCeleb2 (for ASV sub-system training) and ASVspoof 2019 LA database (for CM sub-system training).

Model(s)

ECAPA-TDNN (for speaker verification) and AASIST (for anti-spoofing). Baseline systems used score-level and embedding-level fusion of these models.

Author countries

South Korea, France, Finland

← Previous